公开(公告)号：US20200077023A1

公开(公告)日：2020-03-05

申请号：US16120037

申请日：2018-08-31

Applicant: QUALCOMM Incorporated

Inventor： Young Hoon KANG ,  Hee Jun PARK ,  Tauseef KAZI ,  Ron GAIZMAN ,  Eran PINHASOV ,  Meir TZUR

IPC: H04N5/232 ,  G06N3/08

Abstract: Techniques and systems are provided for machine-learning based image stabilization. In some examples, a system obtains a sequence of frames captured by an image capture device during a period of time, and collects motion sensor measurements calculated by a motion sensor associated with the image capture device based on movement of the image capture device during the period of time. The system generates, using a deep learning network and the motion sensor measurements, parameters for counteracting motions in one or more frames in the sequence of frames, the motions resulting from the movement of the image capture device during the period of time. The system then adjusts the one or more frames in the sequence of frames according to the parameters to generate one or more adjusted frames having a reduction in at least some of the motions in the one or more frames.

公开(公告)号：US20230216999A1

公开(公告)日：2023-07-06

申请号：US17931063

申请日：2022-09-09

Applicant: QUALCOMM Incorporated

Inventor： Pia ZOBEL ,  Yuval SCHWARTZ ,  Tal ZADIK ,  Itschak MARTSIANO ,  Roee HARDOON ,  Meir TZUR ,  Ron GAIZMAN ,  Yehuda PASTERNAK

IPC: H04N13/111 ,  G06T5/00 ,  G06T7/50 ,  G06T7/20

CPC classification number: H04N13/111 ,  G06T5/005 ,  G06T7/50 ,  G06T7/20 ,  G06T2207/20081

Abstract: An imaging system receives depth data (corresponding to an environment) from a depth sensor and first image data (a depiction of the environment) from an image sensor. The imaging system generates, based on the depth data, first motion vectors corresponding to a change in perspective of the depiction of the environment in the first image data. The imaging system generates, using grid inversion based on the first motion vectors, second motion vectors that indicate respective distances moved by respective pixels of the depiction of the environment in the first image data for the change in perspective. The imaging system generates second image data by modifying the first image data according to the second motion vectors. The second image data includes a second depiction of the environment from a different perspective than the first image data. Some image reprojection applications (e.g., frame interpolation) can be performed without the depth data.

公开(公告)号：US20200382706A1

公开(公告)日：2020-12-03

申请号：US16995546

申请日：2020-08-17

Applicant: QUALCOMM Incorporated

Inventor： Young Hoon KANG ,  Hee Jun PARK ,  Tauseef KAZI ,  Ron GAIZMAN ,  Eran PINHASOV ,  Meir TZUR

IPC: H04N5/232 ,  G06N3/08

Abstract: Techniques and systems are provided for machine-learning based image stabilization. In some examples, a system obtains a sequence of frames captured by an image capture device during a period of time, and collects motion sensor measurements calculated by a motion sensor associated with the image capture device based on movement of the image capture device during the period of time. The system generates, using a deep learning network and the motion sensor measurements, parameters for counteracting motions in one or more frames in the sequence of frames, the motions resulting from the movement of the image capture device during the period of time. The system then adjusts the one or more frames in the sequence of frames according to the parameters to generate one or more adjusted frames having a reduction in at least some of the motions in the one or more frames.